PHION Payments

transaction_recovery

Read-onlyIdempotent

Failure classification and non-repeating recovery plan with validated attempt history; 0.010 USDC.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "policy": {
        "deadline": 4102444800,
        "max_attempts": 1,
        "allowed_actions": [
          "retry",
          "request_refund",
          "escalate"
        ],
        "refund_endpoint": "https://seller.example/refunds"
      },
      "payment": {
        "asset": "USDC-address",
        "amount": "15000",
        "network": "eip155:8453",
        "recipient": "seller",
        "transaction": "0x..."
      },
      "attempts": [],
      "assurance": {
        "verdict": "disputed",
        "failed_checks": [
          "successful_status"
        ],
        "request_sha256": "64-hex-characters",
        "payment_settled": true,
        "delivery_verified": false,
        "acceptance_satisfied": false
      },
      "transaction_id": "purchase-42"
    },
    "name": "transaction_recovery"
  }
}

Input Schema

Name	Required	Description	Default
`policy`	Yes
`payment`	Yes
`attempts`	No
`assurance`	Yes
`transaction_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

addedInput schema / examples

Added value: +[
+  {
+    "assurance": {
+      "acceptance_satisfied": false,
+      "delivery_verified": false,
+      "failed_checks": [
+        "successful_status"
+      ],
+      "payment_settled": true,
+      "request_sha256": "64-hex-characters",
+      "verdict": "disputed"
+    },
+    "attempts": [],
+    "payment": {
+      "amount": "15000",
+      "asset": "USDC-address",
+      "network": "eip155:8453",
+      "recipient": "seller",
+      "transaction": "0x..."
+    },
+    "policy": {
+      "allowed_actions": [
+        "retry",
+        "request_refund",
+        "escalate"
+      ],
+      "deadline": 4102444800,
+      "max_attempts": 1,
+      "refund_endpoint": "https://seller.example/refunds"
+    },
+    "transaction_id": "purchase-42"
+  }
+]

First observedSep 24, 2026

TDQS

C2.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is largely covered. The description adds two useful nuggets beyond that: a deterministic 'non-repeating' recovery plan and an explicit 0.010 USDC cost, which is non-obvious for a read-only tool. It still says nothing about determinism guarantees or what the plan contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single tight sentence with the cost front-loaded at the end and no filler. However, brevity here reads as under-specification rather than economy, so it cannot earn full marks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A complex tool with four required params, nested objects, and no output schema needs far more explanation than one clause. The description leaves the agent without argument guidance, return-shape expectations, or sibling differentiation, especially against transaction_recovery_v2.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, including three nested objects (policy, payment, assurance) with no field documentation. The description contributes nothing about any parameter, so it fails to compensate for a serious coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The phrase 'Failure classification and non-repeating recovery plan with validated attempt history' names a recognizable function, but it is a stacked noun phrase rather than a clear verb+resource statement. Critically, it does not distinguish itself from the sibling transaction_recovery_v2, leaving the agent unable to tell which recovery tool to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use, when-not-to-use, or alternative routing guidance. With siblings like transaction_recovery_v2, payment_diagnose, and transaction_assurance, the absence of any selection criteria is a real gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All PHION Payments tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?